Carnegie Mellon Uses LLMs to Correct 3D Prints

Carnegie Mellon University mechanical engineering researchers devised a system that uses multiple large language models to monitor and correct 3D printers in real time. The approach relies on base ChatGPT-4o plus domain-specific structured prompts rather than custom-trained models, addressing reported failure rates around 7% (Prusa3D) and aiming to reduce waste and improve manufacturing competitiveness.